TY - GEN
T1 - Learning Task Sampling Policy for Multitask Learning
AU - Sundararaman, Dhanasekar
AU - Tsai, Henry
AU - Lee, Kuang Huei
AU - Turc, Iulia
AU - Carin, Lawrence
N1 - Publisher Copyright:
© 2021 Association for Computational Linguistics.
PY - 2021
Y1 - 2021
N2 - It has been shown that training multi-task models with auxiliary tasks can improve the target tasks quality through cross-task transfer. However, the importance of each auxiliary task to the primary task is likely not known a priori. While the importance weights of auxiliary tasks can be manually tuned, it becomes practically infeasible with the number of tasks scaling up. To address this, we propose a search method that automatically assigns importance weights. We formulate it as a reinforcement learning problem and learn a task sampling schedule based on evaluation accuracy of the multi-task model. Our empirical evaluation on XNLI and GLUE shows that our method outperforms uniform sampling and the corresponding single-task baseline.
AB - It has been shown that training multi-task models with auxiliary tasks can improve the target tasks quality through cross-task transfer. However, the importance of each auxiliary task to the primary task is likely not known a priori. While the importance weights of auxiliary tasks can be manually tuned, it becomes practically infeasible with the number of tasks scaling up. To address this, we propose a search method that automatically assigns importance weights. We formulate it as a reinforcement learning problem and learn a task sampling schedule based on evaluation accuracy of the multi-task model. Our empirical evaluation on XNLI and GLUE shows that our method outperforms uniform sampling and the corresponding single-task baseline.
UR - http://www.scopus.com/inward/record.url?scp=85129176058&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85129176058
T3 - Findings of the Association for Computational Linguistics, Findings of ACL: EMNLP 2021
SP - 4410
EP - 4415
BT - Findings of the Association for Computational Linguistics, Findings of ACL
A2 - Moens, Marie-Francine
A2 - Huang, Xuanjing
A2 - Specia, Lucia
A2 - Yih, Scott Wen-Tau
PB - Association for Computational Linguistics (ACL)
T2 - 2021 Findings of the Association for Computational Linguistics, Findings of ACL: EMNLP 2021
Y2 - 7 November 2021 through 11 November 2021
ER -